TensorFlow Privacy - training machine learning models with privacy for training data

Google has released TensorFlow Privacy, a free Python library that lets people train TensorFlow models compliant with more stringent user data privacy standards. It uses differential privacy, a technique for training machine learning systems that increases user privacy by letting developers set various trade-offs relating to the amount of noise applied to the user data being processed.

This repository contains the source code for TensorFlow Privacy, a Python library that includes implementations of TensorFlow optimizers for training machine learning models with differential privacy. The library comes with tutorials and analysis tools for computing the privacy guarantees provided.

The TensorFlow Privacy library is under continual development, always welcoming contributions. In particular, we always welcome help towards resolving the issues currently open.